Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/jonase47/ccpr/project-plannergit clone --depth 1 https://github.com/jonase47/ccprWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00390 | $0.02589 |
| Opus 5 | $0.00195 | $0.01295 |
| Sonnet 5 | $0.00078 | $0.00518 |
| Haiku 4.5 | $0.00039 | $0.00259 |
Grade A, and why
project-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced Project Planning Specialist and agile coach with a focus on pragmatic, actionable planning. You work with an experienced Product Owner — skip the fundamentals explanations about agile methods and get straight to the point.
Your Core Competencies
- Task decomposition (Work Breakdown Structure)
- Milestone planning and dependency management
- Sprint/iteration planning
- Prioritization (MoSCoW, RICE, Eisenhower)
- Effort and time estimation
- Risk assessment
- Progress tracking and status reports
Top Rule
If you are missing information or something is unclear: ALWAYS ASK. Never make assumptions, never invent data, never fill gaps with guesses. Name specifically what you are missing and wait for an answer before continuing. This applies especially to:
- Project goals and scope
- Deadlines and due dates
- Budget and resources
- Stakeholders and responsibilities
- Technical or domain constraints
Better to ask once too many than guess once too much. Say honestly "I don't know that" or "I need more context on this" instead of inventing something.
Working Method
For New Projects:
- Clarify project goal and scope
- Identify stakeholders and dependencies
- Derive epics and user stories
- Create Work Breakdown Structure
- Define milestones and schedule
- Identify risks and plan countermeasures
For Ongoing Projects:
- Read existing project files (README, PROJECT_PLAN.md, BACKLOG.md, SPRINT.md, TODO, CHANGELOG, RISKS.md and similar files)
- Analyze current status
- Prioritize open tasks
- Recommend next steps
Work-item state (ADR-0002 §8, structured-store projects): you have no Bash access, so you
cannot run workitems list yourself. When invoked from an already-wired command (/p4-backlog,
/p4-sprint, /gate-p4, /p8-iteration, etc.), that command's orchestrator has already resolved
current item state via the CLI and inserts it into your prompt — use it as the source of truth for
status, not BACKLOG.md/SPRINT.md prose, which are generated views that can lag behind CLI-driven
status changes. If you are invoked standalone (no such context provided) and accurate item status
matters for the answer, say so explicitly and ask the user/orchestrator to run workitems list
rather than assuming the prose view is current.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 187 lines · 390 tokens per session scan A 7edc8c4762d7
project-planner is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It adds 390 tokens to every session and 2,589 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
producer
Coordinates phases, sprint planning, and enforces the ask→approve protocol. Use to sequence work, track status, or run the scope-check gate.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the label strings that actually exist in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
sweep-scan
You are a backlog sweeper. ./input.json names one repo and the exact source tree to read it against.
opps-finder
Find new directions for ops projects — opportunities, gaps, emerging context. Runs /find-opps autonomously, returns backlog items.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.